tanstack-db-playbook-tanstack-db-collections

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow ingests arbitrary outsider-authored free text when data loaded from external REST/WebSocket/Electric streams (e.g., item fields like text) is placed into collections and later consumed, with no AI-specific prompt-injection sanitization shown in the skill docs.